csv 3.2.6 → 3.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 48581eef7d2903fa52d36b48a8c1596396a5957b166c99ea8dcfd14ffb0dc221
-  data.tar.gz: fa6a5cdd9ade30c0a45f7974dcb43128d5e99cc7bf344e9e5b012993ad081ffe
+  metadata.gz: c64817c16c8991fc2596875101449b5452326fe91bd05e4bb6a66213113525d6
+  data.tar.gz: 19d6d80d6959f6cde0ac651774ea795dbd0f949135cae021fef3983d94248f9c
 SHA512:
-  metadata.gz: 00f55443919b4ece138c025818a440ed4a6d0bed64917bcb6f6e810e318f4738f9e129371434c8711173e818b5b58e1d4b2ac2987612617922fda74f03bd3a4b
-  data.tar.gz: 0b83b3b64bf5287653054fa8ecfd4e345f5c41a2a0daedbdba355c4d034bc85c917cf87bd9ee1ede54475ec4e31caadaee54cc2553d529e9ba5b0bc1d5806ff0
+  metadata.gz: 556f6582468d4a3c2994c12c25dba73b8db65e1a10f7306b9b5bc1fa345f47bf7872db1c603ddcd1a0eb359e7857c51a9874be2231dc821730ae62d15604c3b7
+  data.tar.gz: 348a25f4c1bb8e4fe0d71dc944e0a26165627803cb2528fc067642827fd3c253bda48aba179d3575950a7244bd4e8edf2eed9a99101952a07256a3f4f9d1e7fe

data/NEWS.md

@@ -1,5 +1,63 @@
 # News
 
+## 3.2.8 - 2023-11-08
+
+### Improvements
+
+  * Added `CSV::InvalidEncodingError`.
+
+    Patch by Kosuke Shibata.
+
+    GH-287
+
+### Thanks
+
+  * Kosuke Shibata
+
+## 3.2.7 - 2023-06-26
+
+### Improvements
+
+  * Removed an unused internal variable.
+    [GH-273](https://github.com/ruby/csv/issues/273)
+    [Patch by Mau Magnaguagno]
+
+  * Changed to use `https://` instead of `http://` in documents.
+    [GH-274](https://github.com/ruby/csv/issues/274)
+    [Patch by Vivek Bharath Akupatni]
+
+  * Added prefix to a helper module in test.
+    [GH-278](https://github.com/ruby/csv/issues/278)
+    [Patch by Luke Gruber]
+
+  * Added a documentation for `liberal_parsing: {backslash_quotes: true}`.
+    [GH-280](https://github.com/ruby/csv/issues/280)
+    [Patch by Mark Schneider]
+
+### Fixes
+
+  * Fixed a wrong execution result in documents.
+    [GH-276](https://github.com/ruby/csv/issues/276)
+    [Patch by Yuki Tsujimoto]
+
+  * Fixed a bug that the same line is used multiple times.
+    [GH-279](https://github.com/ruby/csv/issues/279)
+    [Reported by Gabriel Nagy]
+
+### Thanks
+
+  * Mau Magnaguagno
+
+  * Vivek Bharath Akupatni
+
+  * Yuki Tsujimoto
+
+  * Luke Gruber
+
+  * Mark Schneider
+
+  * Gabriel Nagy
+
 ## 3.2.6 - 2022-12-08
 
 ### Improvements

data/doc/csv/options/parsing/liberal_parsing.rdoc

@@ -1,13 +1,13 @@
 ====== Option +liberal_parsing+
 
-Specifies the boolean value that determines whether
+Specifies the boolean or hash value that determines whether
 CSV will attempt to parse input not conformant with RFC 4180,
 such as double quotes in unquoted fields.
 
 Default value:
   CSV::DEFAULT_OPTIONS.fetch(:liberal_parsing) # => false
 
-For examples in this section:
+For the next two examples:
   str = 'is,this "three, or four",fields'
 
 Without +liberal_parsing+:
@@ -17,3 +17,22 @@ Without +liberal_parsing+:
 With +liberal_parsing+:
   ary = CSV.parse_line(str, liberal_parsing: true)
   ary # => ["is", "this \"three", " or four\"", "fields"]
+
+Use the +backslash_quote+ sub-option to parse values that use
+a backslash to escape a double-quote character.  This
+causes the parser to treat <code>\"</code> as if it were
+<code>""</code>.
+
+For the next two examples:
+  str = 'Show,"Harry \"Handcuff\" Houdini, the one and only","Tampa Theater"'
+
+With +liberal_parsing+, but without the +backslash_quote+ sub-option:
+  # Incorrect interpretation of backslash; incorrectly interprets the quoted comma as a field separator.
+  ary = CSV.parse_line(str, liberal_parsing: true)
+  ary # => ["Show", "\"Harry \\\"Handcuff\\\" Houdini", " the one and only\"", "Tampa Theater"]
+  puts ary[1] # => "Harry \"Handcuff\" Houdini
+
+With +liberal_parsing+ and its +backslash_quote+ sub-option:
+  ary = CSV.parse_line(str, liberal_parsing: { backslash_quote: true })
+  ary # => ["Show", "Harry \"Handcuff\" Houdini, the one and only", "Tampa Theater"]
+  puts ary[1] # => Harry "Handcuff" Houdini, the one and only

data/doc/csv/recipes/parsing.rdoc

@@ -520,7 +520,7 @@ Apply multiple header converters by defining and registering a custom header con
 To capture unconverted field values, use option +:unconverted_fields+:
   source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n"
   parsed = CSV.parse(source, converters: :integer, unconverted_fields: true)
-  parsed # => [["foo", "0"], ["bar", "1"], ["baz", "2"]]
+  parsed # => [["Name", "Value"], ["foo", 0], ["bar", 1], ["baz", 2]]
   parsed.each {|row| p row.unconverted_fields }
 Output:
   ["Name", "Value"]

data/lib/csv/parser.rb

@@ -101,7 +101,7 @@ class CSV
         position = @scanner.pos
         offset = 0
         n_row_separator_chars = row_separator.size
-        # trace(__method__, :start, line, input)
+        # trace(__method__, :start, input)
         while true
           input.each_line(row_separator) do |line|
             @scanner.pos += line.bytesize
@@ -157,6 +157,7 @@ class CSV
         # trace(__method__, pattern, :done, :last, value) if @last_scanner
         return value if @last_scanner
 
+        # trace(__method__, pattern, :done, :nil) if value.nil?
         return nil if value.nil?
         while @scanner.eos? and read_chunk and (sub_value = @scanner.scan(pattern))
           # trace(__method__, pattern, :sub, sub_value)
@@ -200,7 +201,8 @@ class CSV
           # trace(__method__, :rescan, start, buffer)
           string = @scanner.string
           if scanner == @scanner
-            keep = string.byteslice(start, string.bytesize - start)
+            keep = string.byteslice(start,
+                                    string.bytesize - @scanner.pos - start)
           else
             keep = string
           end
@@ -412,8 +414,7 @@ class CSV
         else
           lineno = @lineno + 1
         end
-        message = "Invalid byte sequence in #{@encoding}"
-        raise MalformedCSVError.new(message, lineno)
+        raise InvalidEncodingError.new(@encoding, lineno)
       rescue UnexpectedError => error
         if @scanner
           ignore_broken_line
@@ -485,7 +486,6 @@ class CSV
           message = ":quote_char has to be nil or a single character String"
           raise ArgumentError, message
         end
-        @double_quote_character = @quote_character * 2
         @escaped_quote_character = Regexp.escape(@quote_character)
         @escaped_quote = Regexp.new(@escaped_quote_character)
       end
@@ -875,8 +875,7 @@ class CSV
               !line.valid_encoding?
             end
             if index
-              message = "Invalid byte sequence in #{@encoding}"
-              raise MalformedCSVError.new(message, @lineno + index + 1)
+              raise InvalidEncodingError.new(@encoding, @lineno + index + 1)
             end
           end
           Scanner.new(string)

data/lib/csv/row.rb

@@ -703,7 +703,7 @@ class CSV
     # by +index_or_header+ and +specifiers+.
     #
     # The nested objects may be instances of various classes.
-    # See {Dig Methods}[https://docs.ruby-lang.org/en/master/dig_methods_rdoc.html].
+    # See {Dig Methods}[rdoc-ref:dig_methods.rdoc].
     #
     # Examples:
     #   source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n"

data/lib/csv/version.rb

@@ -2,5 +2,5 @@
 
 class CSV
   # The version of the installed library.
-  VERSION = "3.2.6"
+  VERSION = "3.2.8"
 end

data/lib/csv.rb

@@ -70,7 +70,7 @@
 # == What is CSV, really?
 #
 # CSV maintains a pretty strict definition of CSV taken directly from
-# {the RFC}[http://www.ietf.org/rfc/rfc4180.txt]. I relax the rules in only one
+# {the RFC}[https://www.ietf.org/rfc/rfc4180.txt]. I relax the rules in only one
 # place and that is to make using this library easier. CSV will parse all valid
 # CSV.
 #
@@ -102,14 +102,6 @@ require_relative "csv/writer"
 
 # == \CSV
 #
-# === In a Hurry?
-#
-# If you are familiar with \CSV data and have a particular task in mind,
-# you may want to go directly to the:
-# - {Recipes for CSV}[doc/csv/recipes/recipes_rdoc.html].
-#
-# Otherwise, read on here, about the API: classes, methods, and constants.
-#
 # === \CSV Data
 #
 # \CSV (comma-separated values) data is a text representation of a table:
@@ -854,6 +846,15 @@ class CSV
     end
   end
 
+  # The error thrown when the parser encounters invalid encoding in CSV.
+  class InvalidEncodingError < MalformedCSVError
+    attr_reader :encoding
+    def initialize(encoding, line_number)
+      @encoding = encoding
+      super("Invalid byte sequence in #{encoding}", line_number)
+    end
+  end
+
   #
   # A FieldInfo Struct contains details about a field's position in the data
   # source it was read from.  CSV will pass this Struct to some blocks that make
@@ -1144,7 +1145,7 @@ class CSV
     #   File.read('t.csv') # => "Name,Value\nFOO,0\nBAR,-1\nBAZ,-2\n"
     #
     # When neither +in_string_or_io+ nor +out_string_or_io+ given,
-    # parses from {ARGF}[https://docs.ruby-lang.org/en/master/ARGF.html]
+    # parses from {ARGF}[rdoc-ref:ARGF]
     # and generates to STDOUT.
     #
     # Without headers:
@@ -1314,8 +1315,8 @@ class CSV
     #
     # Arguments:
     # * Argument +path_or_io+ must be a file path or an \IO stream.
-    # * Argument +mode+, if given, must be a \File mode
-    #   See {Open Mode}[https://ruby-doc.org/core/IO.html#method-c-new-label-Open+Mode].
+    # * Argument +mode+, if given, must be a \File mode.
+    #   See {Access Modes}[https://docs.ruby-lang.org/en/master/File.html#class-File-label-Access+Modes].
     # * Arguments <tt>**options</tt> must be keyword options.
     #   See {Options for Parsing}[#class-CSV-label-Options+for+Parsing].
     # * This method optionally accepts an additional <tt>:encoding</tt> option
@@ -1521,8 +1522,8 @@ class CSV
     #
     # * Argument +path+, if given, must be the path to a file.
     # :include: ../doc/csv/arguments/io.rdoc
-    # * Argument +mode+, if given, must be a \File mode
-    #   See {Open Mode}[IO.html#method-c-new-label-Open+Mode].
+    # * Argument +mode+, if given, must be a \File mode.
+    #   See {Access Modes}[https://docs.ruby-lang.org/en/master/File.html#class-File-label-Access+Modes].
     # * Arguments <tt>**options</tt> must be keyword options.
     #   See {Options for Generating}[#class-CSV-label-Options+for+Generating].
     # * This method optionally accepts an additional <tt>:encoding</tt> option

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: csv
 version: !ruby/object:Gem::Version
-  version: 3.2.6
+  version: 3.2.8
 platform: ruby
 authors:
 - James Edward Gray II
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-12-08 00:00:00.000000000 Z
+date: 2023-11-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -145,7 +145,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.0.dev
+rubygems_version: 3.5.0.dev
 signing_key:
 specification_version: 4
 summary: CSV Reading and Writing